In this project, you’re given a text file with chess tournament results where the information has some structure. Your job is to create an R Markdown file that generates a .CSV file (that could for example be imported into a SQL database) with the following information for all of the players: Player’s Name, Player’s State, Total Number of Points, Player’s Pre-Rating, and Average Pre Chess Rating of Opponents
## [1] "-----------------------------------------------------------------------------------------"
## [2] " Pair | Player Name |Total|Round|Round|Round|Round|Round|Round|Round| "
## [3] " Num | USCF ID / Rtg (Pre->Post) | Pts | 1 | 2 | 3 | 4 | 5 | 6 | 7 | "
## [4] "-----------------------------------------------------------------------------------------"
## [5] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [6] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"#remove the top rows of dat, they do not contain any player data
chess_data <- chess_data[c(5:length(chess_data))]
#remove any consecutive dashes and replace them with a place holder
#the place holder will separate each player's data
chess_data <- str_replace_all(string = chess_data, pattern = "--+", replacement = "@")
#make the data a long string and split it at @
chess_data <- unlist(strsplit(paste(chess_data, collapse = ""), split = "@"))
#remove most symbols and replace them with commas
chess_data <- str_replace_all(string = chess_data, pattern = "([:space:]|-|\\/|\\||\\>)+", replacement = ",")
#regular expressions for player info
#player_id are the 1st digits in string
player_id <- str_sub(str_extract(chess_data, "^,\\d+"), start = 2)
#player_name is made up of the first letter groups and commas
#the commas are replaced by " " and the excess is trimmed off the fron and end
player_name <- str_trim(str_replace_all(str_extract(chess_data, ",([:alpha:]|,)+"), ",", " "))
#player_state is a 2 letter group that comes after a B or U or digit
player_state <- str_sub(str_extract(chess_data, "(B|U|\\d),[:alpha:][:alpha:],\\d"), start = 3, end = 4)
#total_points is 2 digits separted by a .
total_points <- as.numeric(str_extract(chess_data, "\\d\\.\\d"))
#pre_rating is the first group of digits after :,
pre_rating <- as.numeric(str_sub(str_extract(chess_data, ":,\\d+"), start = 3))
#post_rating is the first group of digits after pre_rating
post_rating <- as.numeric(str_replace_all(str_extract(chess_data, ":,.*,\\d+"), pattern = ":,.*,", replacement = ""))
#create a data frame with all of the relevant information
chess_df <- data.frame(player_id, player_name, player_state, total_points, pre_rating, post_rating, stringsAsFactors = FALSE)#function to find a player's opponents average pre rating
avg_pre <- function (chess_data_string){
#extract opponent ids and results from string
history <- str_sub(str_extract(chess_data, "\\d\\.\\d.*[:alpha:][:alpha:]"), start = 5)
#extract just opponents as a list of strings
opponents_as_char <- str_extract_all(history, "\\d+")
#change list of strings to numbers
opponents <- lapply(opponents_as_char, as.numeric)
#helper function that will replace all opponent numbers with their pre_rating
rating_look_up <-function (i){
return (chess_df$pre_rating[i])
}
#use rating_look_up and sum the results
#this is then divided by the number of games played
opp_avg <- round(unlist(lapply(lapply(opponents, rating_look_up), sum))/str_count(history, "\\d+"), 0)
}## Name State Total Pts Pre Rating Post Rating Opp Avg
## 1 GARY HUA ON 6.0 1794 1817 1605
## 2 DAKSHESH DARURI MI 6.0 1553 1663 1469
## 3 ADITYA BAJAJ MI 6.0 1384 1640 1564
## 4 PATRICK H SCHILLING MI 5.5 1716 1744 1574
## 5 HANSHI ZUO MI 5.5 1655 1690 1501
## 6 HANSEN SONG OH 5.0 1686 1687 1519